{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T14:02:52Z","timestamp":1784556172451,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e0 degli Studi di Bari Aldo Moro"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Forecasting future measurements from geographically distributed sensors is essential across many application domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrelation phenomena, that introduce inter-dependencies among nearby locations, that cannot therefore be treated independently by learning algorithms. While some existing approaches can capture such phenomena, they generally model the spatial dimension globally across all locations. On the other hand, the method we propose in this paper, called SPALT, focuses on capturing spatial relationships specifically among time series with similar trends, even if these trends occur at different times, thus modeling the spatio-temporal locality. SPALT leverages linear model trees, which allow us to naturally consider the spatial autocorrelation in a local manner: during the tree-building process, the adopted heuristics aim to group time series exhibiting similar trends into the same node, on which additional features considering the spatial dimension are selectively injected. Additionally, we propose a new pruning strategy, based on Reduced Error Pruning (REP), that also considers the spatio-temporal locality during the tree simplification. Designed for a multi-step setting, SPALT provides forecasts for multiple future time steps across multiple sensors simultaneously. The characteristics exhibited by SPALT can provide significant benefits in different domains, where measurements come from geographically distributed sensors. In this paper, we focus on data produced by sensors located in multiple renewable power plants measuring their energy production at regular, short intervals. Experiments on three real-world datasets demonstrate the effectiveness of SPALT in forecasting the production of energy at different time horizons, and its superior performance in comparison with tree-based models and state-of-the-art neural networks that incorporate both temporal and spatial dimensions.<\/jats:p>","DOI":"10.1007\/s10994-025-06875-1","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T18:26:46Z","timestamp":1758047206000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time series"],"prefix":"10.1007","volume":"114","author":[{"given":"Annunziata","family":"D\u2019Aversa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianvito","family":"Pio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelangelo","family":"Ceci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"6875_CR1","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1016\/j.renene.2019.01.031","volume":"136","author":"Aasim","year":"2019","unstructured":"Aasim, Singh, S. N., & Mohapatra, A. (2019). Repeated wavelet transform based arima model for very short-term wind speed forecasting. Renewable Energy, 136, 758\u2013768.","journal-title":"Renewable Energy"},{"issue":"2","key":"6875_CR2","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1109\/TSTE.2017.2747765","volume":"9","author":"XG Agoua","year":"2018","unstructured":"Agoua, X. G., Girard, R., & Kariniotakis, G. (2018). Short-term spatio-temporal forecasting of photovoltaic power production. IEEE Transaction on Sustainable Energy, 9(2), 538\u2013546.","journal-title":"IEEE Transaction on Sustainable Energy"},{"key":"6875_CR3","doi-asserted-by":"crossref","unstructured":"Altieri, M., Corizzo, R., & Ceci, M. (2024). GAP-LSTM: Graph-based autocorrelation preserving networks for geo-distributed forecasting. IEEE Transactio on Neural Networks and Learning Systems, 1\u201315.","DOI":"10.1109\/TNNLS.2024.3398441"},{"issue":"2","key":"6875_CR4","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1111\/j.1538-4632.1995.tb00338.x","volume":"27","author":"L Anselin","year":"1995","unstructured":"Anselin, L. (1995). Local indicators of spatial association\u2013LISA. Geographical Analysis, 27(2), 93\u2013115.","journal-title":"Geographical Analysis"},{"issue":"10","key":"6875_CR5","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.1016\/j.solener.2009.05.016","volume":"83","author":"P Bacher","year":"2009","unstructured":"Bacher, P., Madsen, H., & Nielsen, H. A. (2009). Online short-term solar power forecasting. Solar Energy, 83(10), 1772\u20131783.","journal-title":"Solar Energy"},{"issue":"1","key":"6875_CR6","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","volume":"57","author":"Y Benjamini","year":"1995","unstructured":"Benjamini, Y., & Hochberg, Y. (1995). Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society. Series B (Methodological), 57(1), 289\u2013300.","journal-title":"Journal of the Royal Statistical Society. Series B (Methodological)"},{"issue":"3","key":"6875_CR7","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/j.ijforecast.2010.09.004","volume":"27","author":"G Bontempi","year":"2011","unstructured":"Bontempi, G., & Ben Taieb, S. (2011). Conditionally dependent strategies for multiple-step-ahead prediction in local learning. International Journal of Forecasting, 27(3), 689\u2013699.","journal-title":"International Journal of Forecasting"},{"key":"6875_CR8","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J., Stone, C.J., & Olshen, R.A. (2017). Classification and regression trees.","DOI":"10.1201\/9781315139470"},{"issue":"3","key":"6875_CR9","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1109\/TII.2016.2604758","volume":"13","author":"M Ceci","year":"2017","unstructured":"Ceci, M., Corizzo, R., Fumarola, F., Malerba, D., & Rashkovska, A. (2017). Predictive modeling of pv energy production: How to set up the learning task for a better prediction? IEEE Transaction on Industrial Informatics, 13(3), 956\u2013966.","journal-title":"IEEE Transaction on Industrial Informatics"},{"issue":"4","key":"6875_CR10","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TSG.2018.2844307","volume":"10","author":"K Chen","year":"2019","unstructured":"Chen, K., Chen, K., Wang, Q., He, Z., Hu, J., & He, J. (2019). Short-term load forecasting with deep residual networks. IEEE Transactions on Smart Grid, 10(4), 3943\u20133952.","journal-title":"IEEE Transactions on Smart Grid"},{"key":"6875_CR11","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-3-031-18840-4_11","volume-title":"Discovery Science","author":"A D\u2019Aversa","year":"2022","unstructured":"D\u2019Aversa, A., Polimena, S., Pio, G., & Ceci, M. (2022). Leveraging spatio-temporal autocorrelation to improve the forecasting of the energy consumption in smart grids. In P. Pascal & D. Ienco (Eds.), Discovery Science (pp. 141\u2013156). Cham: Springer."},{"key":"6875_CR12","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1023\/A:1009868929893","volume":"3","author":"P Domingos","year":"1999","unstructured":"Domingos, P. (1999). The role of occam\u2019s razor in knowledge discovery. Data Mining and Knowledge Discovery, 3, 409\u2013425.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"2","key":"6875_CR13","first-page":"763","volume":"7","author":"J Dowell","year":"2015","unstructured":"Dowell, J., & Pinson, P. (2015). Very-short-term probabilistic wind power forecasts by sparse vector autoregression. IEEE Transactions on Smart Grid, 7(2), 763\u2013770.","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"3\u20134","key":"6875_CR14","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.ecolmodel.2006.02.015","volume":"196","author":"S Dray","year":"2006","unstructured":"Dray, S., Legendre, P., & Peres-Neto, P. R. (2006). Spatial modelling: A comprehensive framework for principal coordinate analysis of neighbour matrices (PCNM). Ecological Modelling, 196(3\u20134), 483\u2013493.","journal-title":"Ecological Modelling"},{"issue":"6","key":"6875_CR15","doi-asserted-by":"publisher","first-page":"2412","DOI":"10.1109\/TKDE.2019.2954510","volume":"33","author":"S Du","year":"2021","unstructured":"Du, S., Li, T., Yang, Y., & Horng, S.-J. (2021). Deep air quality forecasting using hybrid deep learning framework. IEEE Transactions on Knowledge and Data Engineering, 33(6), 2412\u20132424.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"6875_CR16","doi-asserted-by":"crossref","unstructured":"Guo, S., Lin, Y., Feng, N., Song, C., & Wan, H. (2019). Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI 2019, vol. 33, pp. 922\u2013929.","DOI":"10.1609\/aaai.v33i01.3301922"},{"issue":"1","key":"6875_CR17","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1109\/TSTE.2015.2480245","volume":"7","author":"Q Hu","year":"2016","unstructured":"Hu, Q., Zhang, S., Yu, M., & Xie, Z. (2016). Short-term wind speed or power forecasting with heteroscedastic support vector regression. IEEE Transactions on Sustainable Energy, 7(1), 241\u2013249.","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"6875_CR18","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.energy.2016.10.040","volume":"119","author":"P Jiang","year":"2017","unstructured":"Jiang, P., Wang, Y., & Wang, J. (2017). Short-term wind speed forecasting using a hybrid model. Energy, 119, 561\u2013577.","journal-title":"Energy"},{"key":"6875_CR19","doi-asserted-by":"publisher","first-page":"3097","DOI":"10.1109\/TNNLS.2021.3111817","volume":"34","author":"O Karaahmetoglu","year":"2020","unstructured":"Karaahmetoglu, O., & Kozat, S. S. (2020). Spatiotemporal sequence prediction with point processes and self-organizing decision trees. IEEE Transactions on Neural Networks and Learning Systems, 34, 3097\u20133110.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"6875_CR20","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1109\/TSTE.2018.2844102","volume":"10","author":"M Khodayar","year":"2019","unstructured":"Khodayar, M., & Wang, J. (2019). Spatio-temporal graph deep neural network for short-term wind speed forecasting. IEEE Transactions on Sustainable Energy, 10(2), 670\u2013681.","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"6875_CR21","doi-asserted-by":"crossref","unstructured":"Kim, T., Yue, Y., Taylor, S., & Matthews, I. (2015). A decision tree framework for spatiotemporal sequence prediction. In Proceedings of ACM SIGKDD 2015, pp. 577\u2013586. ACM","DOI":"10.1145\/2783258.2783356"},{"issue":"3","key":"6875_CR22","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1109\/TSTE.2019.2926147","volume":"11","author":"C Li","year":"2020","unstructured":"Li, C., Tang, G., Xue, X., Saeed, A., & Hu, X. (2020). Short-term wind speed interval prediction based on ensemble gru model. IEEE Transactions on Sustainable Energy, 11(3), 1370\u20131380.","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"6875_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Dong, Z., Jiang, R., Deng, J., Deng, J., Chen, Q., & Song, X. (2023). Spatio-temporal adaptive embedding makes vanilla transformer sota for traffic forecasting. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. CIKM \u201923, pp. 4125\u20134129. Association for Computing Machinery","DOI":"10.1145\/3583780.3615160"},{"issue":"1","key":"6875_CR24","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/TSTE.2022.3198816","volume":"14","author":"Z Li","year":"2023","unstructured":"Li, Z., Ye, L., Zhao, Y., Pei, M., Lu, P., Li, Y., & Dai, B. (2023). A spatiotemporal directed graph convolution network for ultra-short-term wind power prediction. IEEE Transactions on Sustainable Energy, 14(1), 39\u201354.","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"6875_CR25","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1109\/JSTARS.2020.3040648","volume":"14","author":"C Luo","year":"2021","unstructured":"Luo, C., Li, X., & Ye, Y. (2021). PFST-LSTM: A SpatioTemporal LSTM model with Pseudoflow prediction for precipitation nowcasting. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 843\u2013857.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"issue":"5","key":"6875_CR26","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/TPAMI.2004.1273937","volume":"26","author":"D Malerba","year":"2004","unstructured":"Malerba, D., Esposito, F., Ceci, M., & Appice, A. (2004). Top-down induction of model trees with regression and splitting nodes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5), 612\u2013625.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"6875_CR27","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1016\/j.ijforecast.2018.02.001","volume":"35","author":"JW Messner","year":"2019","unstructured":"Messner, J. W., & Pinson, P. (2019). Online adaptive lasso estimation in vector autoregressive models for high dimensional wind power forecasting. International Journal of Forecasting, 35(4), 1485\u20131498.","journal-title":"International Journal of Forecasting"},{"key":"6875_CR28","unstructured":"Quinlan, J. R. (1992). Learning with continuous classes. In 5th Australian Joint Conference on Artificial Intelligence, vol. 92, pp. 343\u2013348. World Scientific."},{"issue":"3","key":"6875_CR29","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/S0020-7373(87)80053-6","volume":"27","author":"JR Quinlan","year":"1987","unstructured":"Quinlan, J. R. (1987). Simplifying decision trees. International Journal of Man-Machine Studies, 27(3), 221\u2013234.","journal-title":"International Journal of Man-Machine Studies"},{"key":"6875_CR30","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, Z., Wei, W., Wang, F., Xu, Y., Cao, X., & Jensen, C. S. (2022). Decoupled dynamic spatial-temporal graph neural network for traffic forecasting. In Proceedings of the VLDB Endowment, vol. 15, pp. 2733\u20132746.","DOI":"10.14778\/3551793.3551827"},{"key":"6875_CR31","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., & Woo, W.-C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems,28."},{"key":"6875_CR32","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-3-642-24477-3_25","volume-title":"Proceedings of Discovery Science","author":"D Stojanova","year":"2011","unstructured":"Stojanova, D., Ceci, M., Appice, A., Malerba, D., & Dzeroski, S. (2011). Global and local spatial autocorrelation in predictive clustering trees. Proceedings of Discovery Science (pp. 307\u2013322). Springer."},{"issue":"8","key":"6875_CR33","doi-asserted-by":"publisher","first-page":"7067","DOI":"10.1016\/j.eswa.2012.01.039","volume":"39","author":"SB Taieb","year":"2012","unstructured":"Taieb, S. B., Bontempi, G., Atiya, A. F., & Sorjamaa, A. (2012). A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Systems with Applications, 39(8), 7067\u20137083.","journal-title":"Expert Systems with Applications"},{"key":"6875_CR34","unstructured":"Tan, L., & Yue, H. (2023). Application of BERT in wind power forecasting-Teletraan\u2019s solution in Baidu KDD Cup 2022."},{"issue":"4","key":"6875_CR35","doi-asserted-by":"publisher","first-page":"2937","DOI":"10.1109\/TPWRS.2019.2963109","volume":"35","author":"M Tan","year":"2020","unstructured":"Tan, M., Yuan, S., Li, S., Su, Y., Li, H., & He, F. (2020). Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning. IEEE Transactions on Power Systems, 35(4), 2937\u20132948.","journal-title":"IEEE Transactions on Power Systems"},{"issue":"sup1","key":"6875_CR36","doi-asserted-by":"publisher","first-page":"234","DOI":"10.2307\/143141","volume":"46","author":"WR Tobler","year":"1970","unstructured":"Tobler, W. R. (1970). A computer movie simulating urban growth in the detroit region. Economic Geography, 46(sup1), 234\u2013240.","journal-title":"Economic Geography"},{"key":"#cr-split#-6875_CR37.1","unstructured":"Vijayakumar, S., & Schaal, S. (2000). Locally weighted projection regression: An o"},{"key":"#cr-split#-6875_CR37.2","unstructured":"(n) algorithm for incremental real time learning in high dimensional space. In Proceedings of the seventeenth international conference on machine learning (ICML 2000), (pp. 288-293). Morgan Kaufmann Burlington"},{"key":"6875_CR38","doi-asserted-by":"publisher","first-page":"102978","DOI":"10.1016\/j.inffus.2025.102978","volume":"118","author":"P Wang","year":"2025","unstructured":"Wang, P., Feng, L., Zhu, Y., & Wu, H. (2025). Hybrid spatial\u2013temporal graph neural network for traffic forecasting. Information Fusion, 118, 102978.","journal-title":"Information Fusion"},{"key":"6875_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., & Zhang, C. (2019). Graph wavenet for deep spatial-temporal graph modeling. In: Proc. of IJCAI.","DOI":"10.24963\/ijcai.2019\/264"},{"key":"6875_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., & Zhang, C. (2020). Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of ACM SIGKDD 2020, pp. 753\u2013763.","DOI":"10.1145\/3394486.3403118"},{"key":"6875_CR41","doi-asserted-by":"publisher","first-page":"114513","DOI":"10.1016\/j.eswa.2020.114513","volume":"169","author":"R Yan","year":"2021","unstructured":"Yan, R., Liao, J., Yang, J., Sun, W., Nong, M., & Li, F. (2021). Multi-hour and multi-site air quality index forecasting in beijing using cnn, lstm, cnn-lstm, and spatiotemporal clustering. Expert Systems with Applications, 169, 114513.","journal-title":"Expert Systems with Applications"},{"key":"6875_CR42","doi-asserted-by":"crossref","unstructured":"Yao, H., Wu, F., Ke, J., Tang, X., Jia, Y., Lu, S., Gong, P., Ye, J., & Li, Z. (2018). Deep multi-view spatial-temporal network for taxi demand prediction. In Proceedings of the AAAI 2018, vol. 32.","DOI":"10.1609\/aaai.v32i1.11836"},{"key":"6875_CR43","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.solener.2018.10.024","volume":"176","author":"J Zhang","year":"2018","unstructured":"Zhang, J., Verschae, R., Nobuhara, S., & Lalonde, J.-F. (2018). Deep photovoltaic nowcasting. Solar Energy, 176, 267\u2013276.","journal-title":"Solar Energy"},{"key":"6875_CR44","unstructured":"Zhou, J., Lu, X., Xiao, Y., Su, J., Lyu, J., Ma, Y., & Dou, D. (2022). SDWPF: A dataset for spatial dynamic wind power forecasting challenge at KDD Cup 2022. arXiv preprint arXiv:2208.04360."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06875-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06875-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06875-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T20:56:36Z","timestamp":1759870596000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06875-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["6875"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06875-1","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"10 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"231"}}